EPL Analysis and GW 24 Prediction

A data driven attempt in predicting English Premier League results using xG Statistics

This is an article on my EPL Prediction series. You can check out the prediction for Game Week 23 and how it fared against the actual performance here.

Expected Goals or xG is the parameter used for prediction. If you are interested in understanding the algorithm for prediction, I recommend that you check out this article where it is explained in detail.

Analysis up to Game-week 22

EPL Table (Image by Author)

After game week 23, Manchester City are on top of the table with 50 points. Pep Guardiola’s side is 5 points clear of their city rivals, the Red Devils with one game in hand.
Second and Third placed Man United and Leicester dropped points settling for draw against Everton and Wolves respectively.

In the last Game Week, the defending Champions, Liverpool was crushed 1–4 at home by the Citizens, handing them the third successive loss at Anfield. The Reds however ended a 6 match clean sheet streak of Man-City thanks to a penalty kick by Mo Salah.

They (Man City) are running away with the League
-Klopp after Man City Loss

Liverpool despite losing, still remains at fourth position as the Hammers were not able to capitalize on the Reds defeat. The Hammers had to satisfy with one point from Craven Cottege aginst a relegation battling Fulham side.

Chelsea under Tuchel is at Fifth position with 39 points after three consecutive wins. The Spurs rejuvaneted by the return of their captain-Harry Kane, are also back to winning ways after three consecutive losses.

xG Scored vs xG Conceded (Image by Author)

After 23 gameweeks, Man City dominates both attack and defence as it has the highest xG scored and the lowest xG conceded per game. The Reds have dropped to second position following their dismal attacking performance in the recent games. Man United who leads the pack in goals scored is at third position with respect to xG scored. Aston Villa, Leeds and Chelsea have also created more than 1.5xG per game.

Crystal Palace, Burnley, New Castle, Sheffield United and West Brom, struggling with creativity are at the bottom of the league in terms of xG scored per game.
Southampton who have lost all of their last 5 games have been struggling to find the net lately, their xG per game has dropped below 1.

Manchester City seems to the the best defensive unit allowing opponents to create just around 0.70 xG per game. Man City have conceded only one goal in the last 7 games. Chelsea is the only other team which have conceded less than 1 xG per game. After Tuchel took charge, Chelsea has conceded only one goal in 4 games, the only goal conceded being the own goal by Rudiger against Sheff Utd.
Most teams concede between 1 to 1.5 xG per game. West Brom and Leeds have conceded more than 1.5xG per game.

xG Scored vs xG Conceded (Image by Author)

Based on xG Scored and xG Conceded, teams can be grouped into 4 quadrants as shown in the above graph.
The horizontal dotted line shows the average xG scored per game. Teams above the horizontal dotted line are strong attacking sides and the teams below, weak in attack.
The vertical dotted line shows the average xG conceded per game. Teams to the left have a strong defense and the teams to the right have week defense.

Delta xG (Image by Author)

Man City is head and shoulders above the other teams with respect to delta xG, with a differece of more than 1 between xG scored and xG conceded. Liverpool and Chelsea are the the only other teams with delta xG above 0.5. West Brom on the other hand is struggling at both ends of the pitch with the weakest attack and porous defense.

Leeds United ranks among the top in xG created per match. However, the team has negative delta xG as opponents find it easy to penetrate the Leeds defense, something Bielsa has to immediately look into. Wolves on the other hand is a good team defensively, but they lack the strike force with Raul Jiminez out due to injury.
Fulham as per xG stats, is three places clear of relegation. However the Cottagers are languishing in the relegation zone at 17th position. They are not able to convert the xG stats into points as they have conceded 9 draws, the most in the league after Brighton(10 draws).

Game Week 24 Predictions

Before proceeding to the predictions, let me clarify that this is a very simple algorithm just based on past xG, so only baseline performance can be expected. The algorithm also fails to predict high scoring games. The model also does not take into account the team selection, absence of players due to injuries/suspension, formation, tactical changes etc.

However, the model has been performing pretty well in predicting the momentum of the matches. You can check out how the actual performance fared against the predictions made for the previous game week below.

Predictions for Game Week 24 are provided in the table below.
The absolute value of GD shows the competitiveness of the match. The higher the value, more one sided the match is expected to be and higher the accuracy of prediction.
The lower the value of GD, the more the match could be anybody’s game. Positive value of GD means Home win and Negative value means Away team win.

There are 12 matches in GW 24 with Man City, Everton, Fulham and Burnley having Double Game Weeks.

GW 24 Predictions(Image by Author)

Westbrom vs Man United seems to be the most one sided match of Gameweek 24. Man City can expect to comfortably win both of their double game week matches. The Blues can also expect to crush the Magpies at the Bridge.
The Hammers can also expect to secure an easy win over the Blades.

Brighton Vs Villa and Crystal Palace Vs Burnley are clash between equal powers as per the model. No team has edge over the other in those matches.

The defending champions, the Reds will travel to Leicester this weekend. The Reds can snatch the third position if they secure all three points. Dropping points may lead to the Current champions crashing out of Top 4. The xG stats are slightly in favor of the Reds in their next outing.

GW 24 predicted delta xG (Image by Author)

Another high voltage match of the weekend is Saturday’s match between Manchester City and Spurs. It would be great to see what tactics Mourinho would use to trump Pep’s city goal machine. It was Spurs in the reverse fixture in GW 9 who handed the Citizens their last defeat in the league back in November. The algorithm predicts an easy win for City, Spurs performance has been lackluster of late without Harry Kane. Now with Kane back in the squad, Spurs can pose a serious threat to City.
The rivalry between the managers also make the game very interesting.

Update : Predictions vs Actual performance

The algorithm was 87% accurate in predicting the direction of the games where expected goal difference was greater than 0.2. The algorithm was wrong in predicting the outcome of the match between West Brom and Manchester United. As per the algorithm, Man United was estimated to crush the West Brom side. However, we saw West Brom put up a better performance against the Red Devils.
The algorithm predicted Liverpool and Fulham to have an upper hand against Leicester and Burnley, however, the actual performance were in the favor of the hosts.
Arsenal vs Leeds which was predicted to be a high scoring game turned out to be one with the hosts winning 4–2.
Brighton pulled out a very impressive performance vs the Villans, but were denied victory by Villa defense especially goal keeper Martinez who made 9 saves in the match.

Photo by Samuel Regan-Asante on Unsplash

Data Analyst | Hacker | Financial Analyst | Freelancer | IIM MBA | Opensource | Democratize Knowledge | https://www.youtube.com/channel/UCLpBd4gzfIBXm2BPpdHOWdQ